Zobrazeno 1 - 10
of 17
pro vyhledávání: '"Bluche, Theodore"'
We explore a keyword-based spoken language understanding system, in which the intent of the user can directly be derived from the detection of a sequence of keywords in the query. In this paper, we focus on an open-vocabulary keyword spotting method,
Externí odkaz:
http://arxiv.org/abs/2002.10851
In this paper, we propose a fully-neural approach to open-vocabulary keyword spotting, that allows the users to include a customizable voice interface to their device and that does not require task-specific data. We present a keyword detection neural
Externí odkaz:
http://arxiv.org/abs/1912.07575
Autor:
Saade, Alaa, Coucke, Alice, Caulier, Alexandre, Dureau, Joseph, Ball, Adrien, Bluche, Théodore, Leroy, David, Doumouro, Clément, Gisselbrecht, Thibault, Caltagirone, Francesco, Lavril, Thibaut, Primet, Maël
We consider the problem of performing Spoken Language Understanding (SLU) on small devices typical of IoT applications. Our contributions are twofold. First, we outline the design of an embedded, private-by-design SLU system and show that it has perf
Externí odkaz:
http://arxiv.org/abs/1810.12735
Autor:
Coucke, Alice, Saade, Alaa, Ball, Adrien, Bluche, Théodore, Caulier, Alexandre, Leroy, David, Doumouro, Clément, Gisselbrecht, Thibault, Caltagirone, Francesco, Lavril, Thibaut, Primet, Maël, Dureau, Joseph
This paper presents the machine learning architecture of the Snips Voice Platform, a software solution to perform Spoken Language Understanding on microprocessors typical of IoT devices. The embedded inference is fast and accurate while enforcing pri
Externí odkaz:
http://arxiv.org/abs/1805.10190
Autor:
Bluche, Théodore
Offline handwriting recognition systems require cropped text line images for both training and recognition. On the one hand, the annotation of position and transcript at line level is costly to obtain. On the other hand, automatic line segmentation a
Externí odkaz:
http://arxiv.org/abs/1604.08352
We present an attention-based model for end-to-end handwriting recognition. Our system does not require any segmentation of the input paragraph. The model is inspired by the differentiable attention models presented recently for speech recognition, i
Externí odkaz:
http://arxiv.org/abs/1604.03286
Recurrent neural networks (RNNs) with Long Short-Term memory cells currently hold the best known results in unconstrained handwriting recognition. We show that their performance can be greatly improved using dropout - a recently proposed regularizati
Externí odkaz:
http://arxiv.org/abs/1312.4569
Publikováno v:
2016 12th IAPR Workshop on Document Analysis Systems (DAS); 2016, p42-47, 6p
Publikováno v:
2015 13th International Conference on Document Analysis & Recognition (ICDAR); 2015, p681-685, 5p
Publikováno v:
2015 13th International Conference on Document Analysis & Recognition (ICDAR); 2015, p86-90, 5p